Papers with membership inference
Privacy-Preserving Natural Language Processing (2023.eacl-tutorials)
Copied to clipboard
| Challenge: | This tutorial will help the NLP community to get familiar with current research in privacy-preserving methods. |
| Approach: | This tutorial will help the NLP community to get familiar with current research in privacy-preserving methods. |
| Outcome: | The tutorial will cover membership inference, differential privacy, homomorphic encryption, or federated learning, all with typical use-cases and potential pitfalls. |
The Model’s Language Matters: A Comparative Privacy Analysis of LLMs (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models are increasingly deployed in multilingual settings that process sensitive data . prior privacy evaluations focused on English, but new research shows that language matters for privacy leakage . |
| Approach: | They quantify six corpus-level linguistic indicators and evaluate vulnerability under three attack families. |
| Outcome: | The results show that language matters for privacy leakage in large language models . Italian exhibits the strongest exposure, while English and French are more resilient . |
Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods analyze training data with member and non-member contexts, overlooking potential insights from both member and not-member. |
| Approach: | They propose a method that leverages asymmetric distributional shifts induced by member and non-member contexts through contrastive decoding to enhance membership inference. |
| Outcome: | The proposed approach outperforms the current state-of-the-art on the WikiMIA benchmark and is robust against various text manipulation techniques. |
An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models (2022.emnlp-main)
Copied to clipboard
| Challenge: | Large language models are shown to present privacy risks through memorization of training data, but little attention has been given to the fine-tuning phase. |
| Approach: | They empirically study memorization of fine-tuning methods using membership inference and extraction attacks and show that fine-timing the head of the model has the highest susceptibility to attacks. |
| Outcome: | The proposed methods have the highest memorization risk, whereas the smaller adapters are less vulnerable to known extraction attacks. |
Detecting Non-Membership in LLM Training Data via Rank Correlations (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are trained on increasingly vast and opaque text corpora. |
| Approach: | They propose a test that detects dataset-level non-membership using only grey-box access to model logits. |
| Outcome: | The proposed test detects dataset-level non-membership using only grey-box access to model logits. |
AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios (2026.acl-long)
Copied to clipboard
| Challenge: | brittleness of Large Language Models in reasoningintensive tasks is a problem . current compositional benchmarks focus on *either* commonsense or math reasoning . |
| Approach: | They propose a "Co**mmonsense and Ma**th" benchmark where each compositional task requires a commonsense reasoning step *and* a math reasoning step. |
| Outcome: | The proposed benchmarks show that LLMs can solve both steps in isolation, but their accuracy drops by nearly 30% when the two steps are combined. |
R.R.: Unveiling LLM Training Privacy through Recollection and Ranking (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing privacy attacks focus on membership inference or data extraction, but reconstructing specific personally identifiable information (PII) in training data remains challenging. |
| Approach: | They propose a two-step privacy stealing attack that enables attackers to reconstruct PII entities from scrubbed training data where the PI I entities have been masked. |
| Outcome: | The proposed attack can reconstruct PII entities from scrubbed training data where the PI I entities have been masked. |
Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models have revolutionized the field of NLP by achieving state-of-the-art performance on various tasks. |
| Approach: | They investigate the membership inference attack by using model's API to determine if a sample was part of the training data. |
| Outcome: | The proposed model is able to identify if a sample was part of the training data and exploits its similarity and resistance to document modifications as potential MI signals on widely used datasets. |
Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been reported to “leak” Personally Identifiable Information (PII) successful PII reconstruction often interpreted as evidence of memorization. |
| Approach: | They propose a principled revision of memorization evaluation for Large Language Models . they propose PII leakage should be evaluated under low lexical cue conditions . |
| Outcome: | The proposed method is based on a multilingual re-evaluation of PII leakage across 32 languages and multiple memorization paradigms. |